© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 1013
    Prev
    Next
    INDEX
    Explanations

    names of individuals, presumably related to legal or investigative contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    authorized
    -0.76
     initiating
    -0.66
    CLASS
    -0.65
    Whoever
    -0.65
    Interstitial
    -0.64
     assass
    -0.63
    Introdu
    -0.63
    imposed
    -0.63
    regulated
    -0.62
     manoeuv
    -0.61
    POSITIVE LOGITS
     Walters
    1.11
     Robertson
    1.08
     Hughes
    1.08
     McH
    1.08
     Painter
    1.07
     Nichols
    1.07
     Zup
    1.07
     Watkins
    1.06
     Sweeney
    1.05
     McC
    1.05
    Activations Density 0.261%

    No Known Activations